SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03292 · 2026

A3-TTA: Adaptive Anchor Alignment Test-Time Adaptation for Image Segmentation

Shaoting Zhang, Xiangde Luo, Guotai Wang, Yubo Zhou, Jianghao Wu, Lianming Wu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2602.03292.json · badge: /api/ran/2602.03292.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
HiLab-git/A3-TTA community
Papers with Code archive
6 ran · 2 no recorded run
FunctionStatusWhere it lives
ClassRatioLoss Ran
ran on a synthesized input
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("4a0d07671a29d409")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Prototype_Pool Ran
ran on a synthesized input
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("cde46238259ccdbc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_affine Ran
ran; our contract draft was wrong, not the code
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("6177049536217f2c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_invert_affine Ran
ran; our contract draft was wrong, not the code
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("86cad815e8943774")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

copy_model_and_optimizer Ran
ran; our contract draft was wrong, not the code
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("1c838b49ddce9877")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

update_ema_variables Ran
ran; our contract draft was wrong, not the code
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("006d7b109e1c73e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TTA Not yet run
unverified (harvested, no recorded run)
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("91e62e341262d1fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

softmax_entropy Not yet run
unverified (harvested, no recorded run)
HiLab-git/A3-TTA/a3_tta.py
pointer only (licence: NONE) · get_code("3e869ad77e4775a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, HiLab-git/A3-TTA when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Test-Time Adaptation (TTA) offers a practical solution for deploying image segmentation models under domain shift without accessing source data or retraining. Among existing TTA strategies, pseudo-label-based methods have shown promising performance. However, they often rely on perturbation-ensemble heuristics (e.g., dropout sampling, test-time augmentation, Gaussian noise), which lack distributional grounding and yield unstable training signals. This can trigger error accumulation and catastrophic forgetting during adaptation. To address this, we propose A3-TTA, a TTA framework that constructs reliable pseudo-labels through anchor-guided supervision. Specifically, we identify well-predicted target domain images using a class compact density metric, under the assumption that confident predictions imply distributional proximity to the source domain. These anchors serve as stable references to guide pseudo-label generation, which is further regularized via semantic consistency and boundary-aware entropy minimization. Additionally, we introduce a self-adaptive exponential moving average strategy to mitigate label noise and stabilize model update during adaptation. Evaluated on both multi-domain medical images (heart structure and prostate segmentation) and natural images, A3-TTA significantly improves average Dice scores by 10.40 to 17.68 percentage points compared to the source model, outperforming several state-of-the-art TTA methods under different segmentation model architectures. A3-TTA also excels in continual TTA, maintaining high performance across sequential target domains with strong anti-forgetting ability. The code will be made publicly available at https://github.com/HiLab-git/A3-TTA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2602.03292")
get_code_for_paper("2602.03292")
have("2602.03292")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2602.03292.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2602.03292.svg)](https://syntology.ai/paper/2602.03292)

Connect an agent — have() is free.